Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dawson, Fiifi, Mosunmola, Zainab, Pocker, Sahil, Dandekar, Raj Abhijit, Dandekar, Rajat, Panat, Sreedath
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909333172781056
author Dawson, Fiifi
Mosunmola, Zainab
Pocker, Sahil
Dandekar, Raj Abhijit
Dandekar, Rajat
Panat, Sreedath
author_facet Dawson, Fiifi
Mosunmola, Zainab
Pocker, Sahil
Dandekar, Raj Abhijit
Dandekar, Rajat
Panat, Sreedath
contents Although LLMs have been extremely effective in a large number of complex tasks, their understanding and functionality for regional languages and cultures are not well studied. In this paper, we explore the ability of various LLMs to comprehend the cultural aspects of two regional languages: Malayalam (state of Kerala, India) and Yoruba (West Africa). Using Hofstede's six cultural dimensions: Power Distance (PDI), Individualism (IDV), Motivation towards Achievement and Success (MAS), Uncertainty Avoidance (UAV), Long Term Orientation (LTO), and Indulgence (IVR), we quantify the cultural awareness of LLM-based responses. We demonstrate that although LLMs show a high cultural similarity for English, they fail to capture the cultural nuances across these 6 metrics for Malayalam and Yoruba. We also highlight the need for large-scale regional language LLM training with culturally enriched datasets. This will have huge implications for enhancing the user experience of chat-based LLMs and also improving the validity of large-scale LLM agent-based market research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English
Dawson, Fiifi
Mosunmola, Zainab
Pocker, Sahil
Dandekar, Raj Abhijit
Dandekar, Rajat
Panat, Sreedath
Computers and Society
Artificial Intelligence
Computation and Language
Although LLMs have been extremely effective in a large number of complex tasks, their understanding and functionality for regional languages and cultures are not well studied. In this paper, we explore the ability of various LLMs to comprehend the cultural aspects of two regional languages: Malayalam (state of Kerala, India) and Yoruba (West Africa). Using Hofstede's six cultural dimensions: Power Distance (PDI), Individualism (IDV), Motivation towards Achievement and Success (MAS), Uncertainty Avoidance (UAV), Long Term Orientation (LTO), and Indulgence (IVR), we quantify the cultural awareness of LLM-based responses. We demonstrate that although LLMs show a high cultural similarity for English, they fail to capture the cultural nuances across these 6 metrics for Malayalam and Yoruba. We also highlight the need for large-scale regional language LLM training with culturally enriched datasets. This will have huge implications for enhancing the user experience of chat-based LLMs and also improving the validity of large-scale LLM agent-based market research.
title Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and English
topic Computers and Society
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.01811